The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted data from code repositories, such as pull request descriptions, commit messages, and file contents. This creates a surface for indirect prompt injection attacks where malicious instructions embedded in the data could manipulate the agent's behavior. * Ingestion points: Code diffs, repository files, and PR/issue descriptions processed during the 'Scope' and 'Brief' stages. * Capability inventory: The skill has file-write permissions for applying 'fixes' (Step 6) and can execute local Python scripts (Step 1). * Boundary markers: No explicit delimiters or instructions are provided to the reviewer agents to ignore commands contained within the source material. * Sanitization: The skill does not verify or sanitize the content of the repository files or metadata before passing it to the AI models.
[COMMAND_EXECUTION]: The skill executes a local Python script (resolve-scope.py) from a sibling skill's directory. It also orchestrates the execution of other skills (code-review, adversarial-review, review-triage), assuming they are available in the local environment.

review-panel